paper-with-me

Papers

BMAM: Brain-inspired Multi-Agent Memory Framework

2026-01-28 · Yang Li, Jiaxiang Liu, Yusong Wang, Yujie Wu, Mingkun Xu arxiv

Language-model-based agents operating over extended interaction horizons face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions, a failure mode we term soul erosion. We present BMAM (Brain-inspired Multi-Agent Memory), a general-purpose memory architecture that models agent memory as a set of functionally specialized subsystems rather than a single unstructured store. Inspired by cognitive memory systems, BMAM decomposes memory into episodic, semantic, salience-aware, and control-oriented components that operate at complementary time scales. To support long-horizon reasoning, BMAM organizes episodic memories along explicit timelines and retrieves evidence by fusing multiple complementary signals. Experiments on the LoCoMo benchmark show that BMAM achieves 78.45 percent accuracy under the standard long-horizon evaluation setting, and ablation analyses confirm that the hippocampus-inspired episodic memory subsystem plays a critical role in temporal reasoning.

📄 PDF Abstract BibTeX arXiv:2601.20465

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MBMamba: When Memory Buffer Meets Mamba for Structure-Aware Image Deblurring

2025-08-17 · Hu Gao, Xiaoning Lei, Xichen Xu, Depeng Dang 외 arxiv

The Mamba architecture has emerged as a promising alternative to CNNs and Transformers for image deblurring. However, its flatten-and-scan strategy often results in local pixel forgetting and channel redundancy, limiting…

Image Deblurring

BIMRL: Brain Inspired Meta Reinforcement Learning

2022-10-29 · Seyed Roozbeh Razavi Rohani, Saeed Hedayatian, Mahdieh Soleymani Baghshah

Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt a…

Meta Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning

2026-03-12 · Xiaoyu Ma, Lianyu Hu, Wenbing Tang, Zixuan Hu 외 arxiv

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most …

Prompt EngineeringKnowledge Graphs

ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning

2026-04-09 · Daichi Yashima, Shuhei Kurita, Yusuke Oda, Shuntaro Suzuki 외 arxiv

In this study, we focus on video captioning by fully open multimodal large language models (MLLMs). The comprehension of visual sequences is challenging because of their intricate temporal dependencies and substantial se…

Video Captioning

RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems

2025-08-02 · Mingcong Lei, Honghao Cai, Yuyuan Yang, Yimou Wu 외 arxiv

Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial rea…

Spatial Reasoning